Legal claims defining the scope of protection, as filed with the USPTO.
1. A system for displaying a plurality of checkpoint widgets on a workstation used by a supervisor in a contact center, wherein each checkpoint widget indicates one or more checkpoint status indicators of a respective voice call, where each checkpoint status indicator is associated with a respective checkpoint during the respective voice call processed by a call handler involving an agent in the contact center, the system comprising: a real-time speech analytics (“RTSA”) system configured to report a corresponding event message for each keyword detected during the respective voice call involving the agent; a checkpoint and alert reporting module comprising a processor configured to: receive a specific event message from the RTSA system, correlate the specific event message to a particular checkpoint, store timing information in association with the particular checkpoint; and a workstation comprising a computer display and an audio interface, wherein the workstation is configured to display the plurality of checkpoint widgets associated with the agent, wherein at least one checkpoint widget visually distinguishes a particular checkpoint status indicator to reflect absence of speech to be detected for a corresponding checkpoint of the at least one checkpoint widget, wherein the processor of the checkpoint and alert reporting module is further configured to: receive a first request from the workstation for the plurality of checkpoint widgets associated with the agent, the first request further comprising filter information identifying the agent and a time period of calls handled by the agent, wherein the filter information is used to identify the plurality of checkpoint widgets; cause the plurality of checkpoint widgets to be displayed on the workstation, wherein one of the checkpoint widgets comprises the particular checkpoint; receive a second request from the workstation, the second request indicating the particular checkpoint; and cause a portion of audio of a particular call associated with the particular checkpoint to be streamed to the audio interface of the workstation.
2. The system of claim 1 , wherein each checkpoint widget visually depicts: a time-line representing passage of time during the respective voice call; and a plurality of checkpoint status indicators overlaid on the time-line, wherein at least one of the plurality of status indicators reflects detection of speech at the corresponding checkpoint.
3. The system of claim 2 , wherein the portion of audio of the particular call associated with the particular checkpoint to be streamed to the audio interface of the workstation begins at a time that is after a prior checkpoint of the particular call.
4. The system of claim 1 , wherein the workstation is further configured to display a score total associated with each of the checkpoint widgets.
5. The system of claim 1 , wherein the call handler comprises the alert and checkpoint reporting module, and wherein the call handler establishes a first call leg to the RTSA system, a second call leg to the workstation, and a third call leg to a remote party.
6. The system of claim 1 , wherein a plurality of checkpoint status indicator text is displayed with the plurality of checkpoint widgets.
7. The system of claim 1 , wherein streaming the audio to the interface of the workstation comprises retrieving audio of the call into a memory, from which the audio is streamed to the audio interface.
8. The system of claim 7 , further comprising: a file store comprising the memory, wherein the memory stores audio of calls involving the agent, including the audio from the particular call.
9. A non-transitory computer readable medium storing instructions that when executed by a processor in call handler system cause the processor to: receive an event message from a real-time speech analytics system (RTSA system) associated with a voice call between an agent in a contact center agent and a remote party, the event message reporting detection of a keyword spoken by the agent; determine that the event message correlates with a particular checkpoint associated with the voice call; receive a first request from a workstation for a plurality of checkpoint widgets associated with the agent, the first request further comprising filter information identifying the agent and a time period of calls handled by the agent, wherein the filter information is used to identify the plurality of checkpoint widgets; cause the plurality of checkpoint widgets to be displayed on the workstation, wherein one of the plurality of checkpoint widgets comprises the particular checkpoint, and wherein the one of the plurality of checkpoint widgets visually reflects an absence of speech to be detected for another checkpoint of the one of the plurality of checkpoint widgets; receive a second request from the workstation, the second request indicating the particular checkpoint; and cause a portion of audio of the voice call associated with the particular checkpoint to be streamed to an audio interface of the workstation.
10. The non-transitory computer readable medium of claim 9 , wherein the filter information identifying the time period of calls handled by the agent indicates a date, a beginning time on that date, and an ending time on that date.
11. The non-transitory computer readable medium of claim 9 , further comprising instructions that when executed cause the processor to: cause the plurality of checkpoint widgets to be displayed on the workstation with a corresponding score for each of the plurality of checkpoint widgets.
12. The non-transitory computer readable medium of claim 11 , further comprising instructions that when executed cause the processor to: in response to receiving the second request indicating the particular checkpoint, present a user with a window on a computer display, the window displaying controls of an audio player configured to allow the user to control the audio of the voice call.
13. The non-transitory computer readable medium of claim 9 , further comprising instructions that when executed cause the processor to: receive a corresponding text from a user associated with each checkpoint prior to the call handler processing the call; store an association between the corresponding text and a particular event message; and display the corresponding text for each checkpoint on the checkpoint widget during the call when the event message corresponds to the particular event message.
14. The non-transitory computer readable medium of claim 9 , further comprising instructions that when executed cause the processor to: cause the workstation to display the checkpoint widget in an initial display state to the agent on a computer display at a beginning of the voice call.
15. A method for streaming a stored portion of audio of a voice call involving an agent in a contact center comprising: establishing the voice call involving a plurality of call legs, with a first call leg between a remote party and a call handler, a second call leg between the call handler and a real-time speech analytics system (“RTSA system”), and a third call leg between the call handler and a telephone device used by the agent; monitoring the speech of the agent on the second call leg by the RTSA system; generating an event message from the RTSA system to the call handler in response to detecting a previously indicated keyword on the voice call; receiving the event message at the call handler; determining that the event message reflects detection of a keyword associated with a particular checkpoint of the voice call; storing timing information of the audio of the call based on the event message; receiving a first request from a workstation for a plurality of checkpoint widgets associated with the agent, the first request further comprising filter information identifying the agent and a time period of calls handled by the agent, wherein the filter information is used to identify the plurality of checkpoint widgets; causing the plurality of checkpoint widgets to be displayed on the workstation, wherein one of the checkpoint widgets comprises the particular checkpoint, and wherein at least another one of the checkpoint widgets visually reflects an absence of speech to be detected for another checkpoint corresponding to the at least another one of the checkpoint widgets; receiving a second request from the workstation, the second request indicating the particular checkpoint; and causing the portion of the stored audio of the voice call associated with the particular checkpoint to be streamed to an interface of the workstation.
16. The method of claim 15 , wherein causing the plurality of checkpoint widgets to be displayed on the workstation further causes a corresponding score to be displayed with each checkpoint widget.
17. The method of claim 15 , wherein the time period of calls handled by the agent comprises a date, beginning time, and ending time.
18. The method of claim 15 , wherein the timing information of the audio of the voice call comprises an offset time from a beginning of the voice call.
19. The method of claim 18 , wherein the offset is based on a predefined backup time offset from the particular checkpoint.
Unknown
October 13, 2015
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.